Indexing the Event Calculus: Towards practical human-readable Personal Health Systems

Nicola Falcionelli, Paolo Sernani, Albert Brugués, Dagmawi Neway Mekuria, Davide Calvaresi, Michael Schumacher, Aldo Franco Dragoni, Stefano Bromuri

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Personal Health Systems (PHS) are mobile solutions tailored to monitoring patients affected by chronic non communicable diseases. In general, a patient affected by a chronic disease can generate large amounts of events: for example, in Type 1 Diabetic patients generate several glucose events per day, ranging from at least 6 events per day (under normal monitoring) to 288 per day when wearing a continuous glucose monitor (CGM) that samples the blood every 5 minutes for several days. Just by itself, without considering other physiological parameters, it would be impossible for medical doctors to individually and accurately follow every patient, highlighting the need of simple approaches towards querying physiological time series. Achieving this with current technology is not an easy task, as on one hand it cannot be expected that medical doctors have the technical knowledge to query databases and on the other hand these time series include thousands of events, which requires to re-think the way data is indexed. Anyhow, handling data streams efficiently is not enough. Domain experts' knowledge must be explicitly included into PHSs in a way that it can be easily readed and modified by medical staffs. Logic programming represents the perfect programming paradygm to accomplish this task. In this work, an Event Calculus-based reasoning framework to standardize and express domain-knowledge in the form of monitoring rules is suggested, and applied to three different use cases. However, if online monitoring has to be achieved, the reasoning performance must improve dramatically. For this reason, three promising mechanisms to index the Event Calculus Knowledge Base are proposed. All of them are based on different types of tree indexing structures: k-d trees, interval trees and red-black trees. The paper then compares and analyzes the performance of the three indexing techniques, by computing the time needed to check different type of rules (and eventually generating alerts), when the number of recorded events (e.g. values of physiological parameters) increases. The results show that customized jREC performs much better when the event average inter-arrival time is little compared to the checked rule time-window. Instead, where the events are more sparse, the use of k-d trees with standard EC is advisable. Finally, the Multi-Agent paradigm helps to wrap the various components of the system: the reasoning engines represent the agent minds, and the sensors are its body. The said agents have been developed in MAGPIE, a mobile event based Java agent platform.
Original languageEnglish
Pages (from-to)154-166
Number of pages13
JournalArtificial Intelligence in Medicine
Volume96
Early online date13 Nov 2018
DOIs
Publication statusPublished - May 2019

Fingerprint

Calculi
Health
Glucose
Monitoring
Time series
Patient monitoring
Data handling
Logic programming
Computer programming
Blood
Knowledge Bases
Telemedicine
Engines
Medical Staff
Physiologic Monitoring
Sensors
Communicable Diseases
Chronic Disease
Databases
Technology

Keywords

  • Logic programming
  • Event calculus
  • Knowledge representation
  • reasoning
  • prolog
  • Personal health systems
  • Multi-agent systems

Cite this

Falcionelli, Nicola ; Sernani, Paolo ; Brugués, Albert ; Mekuria, Dagmawi Neway ; Calvaresi, Davide ; Schumacher, Michael ; Dragoni, Aldo Franco ; Bromuri, Stefano. / Indexing the Event Calculus : Towards practical human-readable Personal Health Systems. In: Artificial Intelligence in Medicine. 2019 ; Vol. 96. pp. 154-166.
@article{cdc7fcc989f048cba6cae4118b2afd3f,
title = "Indexing the Event Calculus: Towards practical human-readable Personal Health Systems",
abstract = "Personal Health Systems (PHS) are mobile solutions tailored to monitoring patients affected by chronic non communicable diseases. In general, a patient affected by a chronic disease can generate large amounts of events: for example, in Type 1 Diabetic patients generate several glucose events per day, ranging from at least 6 events per day (under normal monitoring) to 288 per day when wearing a continuous glucose monitor (CGM) that samples the blood every 5 minutes for several days. Just by itself, without considering other physiological parameters, it would be impossible for medical doctors to individually and accurately follow every patient, highlighting the need of simple approaches towards querying physiological time series. Achieving this with current technology is not an easy task, as on one hand it cannot be expected that medical doctors have the technical knowledge to query databases and on the other hand these time series include thousands of events, which requires to re-think the way data is indexed. Anyhow, handling data streams efficiently is not enough. Domain experts' knowledge must be explicitly included into PHSs in a way that it can be easily readed and modified by medical staffs. Logic programming represents the perfect programming paradygm to accomplish this task. In this work, an Event Calculus-based reasoning framework to standardize and express domain-knowledge in the form of monitoring rules is suggested, and applied to three different use cases. However, if online monitoring has to be achieved, the reasoning performance must improve dramatically. For this reason, three promising mechanisms to index the Event Calculus Knowledge Base are proposed. All of them are based on different types of tree indexing structures: k-d trees, interval trees and red-black trees. The paper then compares and analyzes the performance of the three indexing techniques, by computing the time needed to check different type of rules (and eventually generating alerts), when the number of recorded events (e.g. values of physiological parameters) increases. The results show that customized jREC performs much better when the event average inter-arrival time is little compared to the checked rule time-window. Instead, where the events are more sparse, the use of k-d trees with standard EC is advisable. Finally, the Multi-Agent paradigm helps to wrap the various components of the system: the reasoning engines represent the agent minds, and the sensors are its body. The said agents have been developed in MAGPIE, a mobile event based Java agent platform.",
keywords = "Logic programming, Event calculus, Knowledge representation, reasoning, prolog, Personal health systems, Multi-agent systems",
author = "Nicola Falcionelli and Paolo Sernani and Albert Brugu{\'e}s and Mekuria, {Dagmawi Neway} and Davide Calvaresi and Michael Schumacher and Dragoni, {Aldo Franco} and Stefano Bromuri",
note = "Copyright {\circledC} 2018 Elsevier B.V. All rights reserved.",
year = "2019",
month = "5",
doi = "10.1016/j.artmed.2018.10.003",
language = "English",
volume = "96",
pages = "154--166",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",

}

Falcionelli, N, Sernani, P, Brugués, A, Mekuria, DN, Calvaresi, D, Schumacher, M, Dragoni, AF & Bromuri, S 2019, 'Indexing the Event Calculus: Towards practical human-readable Personal Health Systems', Artificial Intelligence in Medicine, vol. 96, pp. 154-166. https://doi.org/10.1016/j.artmed.2018.10.003

Indexing the Event Calculus : Towards practical human-readable Personal Health Systems. / Falcionelli, Nicola; Sernani, Paolo; Brugués, Albert; Mekuria, Dagmawi Neway; Calvaresi, Davide; Schumacher, Michael; Dragoni, Aldo Franco; Bromuri, Stefano.

In: Artificial Intelligence in Medicine, Vol. 96, 05.2019, p. 154-166.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Indexing the Event Calculus

T2 - Towards practical human-readable Personal Health Systems

AU - Falcionelli, Nicola

AU - Sernani, Paolo

AU - Brugués, Albert

AU - Mekuria, Dagmawi Neway

AU - Calvaresi, Davide

AU - Schumacher, Michael

AU - Dragoni, Aldo Franco

AU - Bromuri, Stefano

N1 - Copyright © 2018 Elsevier B.V. All rights reserved.

PY - 2019/5

Y1 - 2019/5

N2 - Personal Health Systems (PHS) are mobile solutions tailored to monitoring patients affected by chronic non communicable diseases. In general, a patient affected by a chronic disease can generate large amounts of events: for example, in Type 1 Diabetic patients generate several glucose events per day, ranging from at least 6 events per day (under normal monitoring) to 288 per day when wearing a continuous glucose monitor (CGM) that samples the blood every 5 minutes for several days. Just by itself, without considering other physiological parameters, it would be impossible for medical doctors to individually and accurately follow every patient, highlighting the need of simple approaches towards querying physiological time series. Achieving this with current technology is not an easy task, as on one hand it cannot be expected that medical doctors have the technical knowledge to query databases and on the other hand these time series include thousands of events, which requires to re-think the way data is indexed. Anyhow, handling data streams efficiently is not enough. Domain experts' knowledge must be explicitly included into PHSs in a way that it can be easily readed and modified by medical staffs. Logic programming represents the perfect programming paradygm to accomplish this task. In this work, an Event Calculus-based reasoning framework to standardize and express domain-knowledge in the form of monitoring rules is suggested, and applied to three different use cases. However, if online monitoring has to be achieved, the reasoning performance must improve dramatically. For this reason, three promising mechanisms to index the Event Calculus Knowledge Base are proposed. All of them are based on different types of tree indexing structures: k-d trees, interval trees and red-black trees. The paper then compares and analyzes the performance of the three indexing techniques, by computing the time needed to check different type of rules (and eventually generating alerts), when the number of recorded events (e.g. values of physiological parameters) increases. The results show that customized jREC performs much better when the event average inter-arrival time is little compared to the checked rule time-window. Instead, where the events are more sparse, the use of k-d trees with standard EC is advisable. Finally, the Multi-Agent paradigm helps to wrap the various components of the system: the reasoning engines represent the agent minds, and the sensors are its body. The said agents have been developed in MAGPIE, a mobile event based Java agent platform.

AB - Personal Health Systems (PHS) are mobile solutions tailored to monitoring patients affected by chronic non communicable diseases. In general, a patient affected by a chronic disease can generate large amounts of events: for example, in Type 1 Diabetic patients generate several glucose events per day, ranging from at least 6 events per day (under normal monitoring) to 288 per day when wearing a continuous glucose monitor (CGM) that samples the blood every 5 minutes for several days. Just by itself, without considering other physiological parameters, it would be impossible for medical doctors to individually and accurately follow every patient, highlighting the need of simple approaches towards querying physiological time series. Achieving this with current technology is not an easy task, as on one hand it cannot be expected that medical doctors have the technical knowledge to query databases and on the other hand these time series include thousands of events, which requires to re-think the way data is indexed. Anyhow, handling data streams efficiently is not enough. Domain experts' knowledge must be explicitly included into PHSs in a way that it can be easily readed and modified by medical staffs. Logic programming represents the perfect programming paradygm to accomplish this task. In this work, an Event Calculus-based reasoning framework to standardize and express domain-knowledge in the form of monitoring rules is suggested, and applied to three different use cases. However, if online monitoring has to be achieved, the reasoning performance must improve dramatically. For this reason, three promising mechanisms to index the Event Calculus Knowledge Base are proposed. All of them are based on different types of tree indexing structures: k-d trees, interval trees and red-black trees. The paper then compares and analyzes the performance of the three indexing techniques, by computing the time needed to check different type of rules (and eventually generating alerts), when the number of recorded events (e.g. values of physiological parameters) increases. The results show that customized jREC performs much better when the event average inter-arrival time is little compared to the checked rule time-window. Instead, where the events are more sparse, the use of k-d trees with standard EC is advisable. Finally, the Multi-Agent paradigm helps to wrap the various components of the system: the reasoning engines represent the agent minds, and the sensors are its body. The said agents have been developed in MAGPIE, a mobile event based Java agent platform.

KW - Logic programming

KW - Event calculus

KW - Knowledge representation

KW - reasoning

KW - prolog

KW - Personal health systems

KW - Multi-agent systems

U2 - 10.1016/j.artmed.2018.10.003

DO - 10.1016/j.artmed.2018.10.003

M3 - Article

C2 - 30442433

VL - 96

SP - 154

EP - 166

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

ER -